Skip to main content
Glama

open-meteo-mcp-server

by io.github.cyanheads

Openmeteo Get Air Quality

openmeteo_get_air_quality
Read-onlyIdempotent

Modeled CAMS (Copernicus Atmosphere Monitoring Service) air quality: PM2.5, PM10, nitrogen dioxide, sulphur dioxide, ozone, carbon monoxide, dust, pollen, and European/US AQI indices. This is modeled grid data, not measured station readings — for measured data, use openaq-mcp-server. Forecast horizon up to 7 days, with optional past_days (up to 92) for recent history — or start_date and end_date together for an archive range, which returns real CAMS values back to at least 2022-10-01. One window per call: a date range is mutually exclusive with forecast_days and past_days, and needs both ends — a lone start_date or end_date is rejected. Common variables: pm2_5, pm10, carbon_monoxide, nitrogen_dioxide, sulphur_dioxide, ozone, dust, european_aqi, us_aqi, alder_pollen, birch_pollen, grass_pollen, mugwort_pollen, olive_pollen, ragweed_pollen. A wide window — a large past_days or date range plus many variables — produces thousands of records; these spill to DataCanvas for SQL querying when canvas is enabled, and return a bounded preview with truncated: true when it is not.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
end_dateNoEnd date for the archive range (YYYY-MM-DD, inclusive). Must be on or after start_date. Requires start_date — the pair must be sent together, and neither combines with forecast_days or past_days.
latitudeYesLatitude in decimal degrees. Use openmeteo_search_locations to resolve a place name.
timezoneNoIANA timezone or "auto". Default "auto".auto
canvas_idNoDataCanvas token for wide past_days, archive-range, or multi-variable queries. When a result is too large to return inline — driven by total payload size, so a wide multi-variable pull can spill at any row count — it spills to this canvas for SQL querying. Omit to create a fresh canvas.
longitudeYesLongitude in decimal degrees.
past_daysNoInclude this many days of past data before today (0–92). Use for recent history instead of a start_date/end_date range. Default 0. Must stay 0 when start_date/end_date are used.
start_dateNoStart date for the archive range (YYYY-MM-DD, e.g., "2024-07-01"). Real CAMS values go back to at least 2022-10-01; earlier dates return rows of nulls. Requires end_date — the pair must be sent together, and neither combines with forecast_days or past_days.
forecast_daysNoForecast horizon in days (1–7). Omit for the upstream default of 5. Mutually exclusive with start_date/end_date — omit it entirely when pulling an archive range.
hourly_variablesNoHourly air quality variables (e.g., ["pm2_5", "pm10", "ozone", "nitrogen_dioxide", "european_aqi", "us_aqi"]). At least one required.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
hourlyNoPer-hour records with "time" (ISO 8601) + one key per requested variable. Units: pm2_5/pm10/dust in μg/m³, carbon_monoxide in μg/m³, nitrogen_dioxide/sulphur_dioxide/ozone in μg/m³, european_aqi/us_aqi as index values. When truncated, contains only a preview — query canvas_id for the full dataset when one is present.
noticeNoWarning that a requested variable came back with no data — names each column whose unit is "undefined", which is how the endpoint reports a name it parsed but does not serve.
latitudeNoSnapped latitude
timezoneNoResolved IANA timezone
canvas_idNoDataCanvas token for the staged full dataset. Present only when truncated is true AND DataCanvas is enabled (CANVAS_PROVIDER_TYPE=duckdb) — absent otherwise, in which case the preview is all this response carries. Query with SQL using this token.
longitudeNoSnapped longitude
truncatedNoTrue when the response was too large to return inline, so hourly carries a bounded preview rather than the full set. With DataCanvas enabled the complete data is staged at canvas_id. With it disabled there is no canvas_id, and the omitted rows are reached only by narrowing the request.
table_nameNoDuckDB table name for the staged data — pass to openmeteo_dataframe_query. Present only alongside canvas_id.
data_sourceNoData source identifier — this is modeled CAMS data, forecast or archive, not measured station data.
hourly_unitsNoVariable → unit string for hourly data (e.g., {"pm2_5": "μg/m³", "european_aqi": "EAQI"}).
record_countNoTotal number of hourly records — the full upstream total when truncated is true, not the length of the hourly preview.

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds significant context beyond annotations: it explains the modeled vs measured distinction, the data spill behavior to DataCanvas for large windows, and the 7-day forecast limit with past days up to 92. The 'real CAMS values back to at least 2022-10-01' and 'earlier dates return nulls' notes are particularly valuable. Since readOnlyHint and idempotentHint are already set, the description doesn't need to repeat those; it focuses on data characteristics. Minor deduction: it doesn't explicitly state that results are bounded previews with truncated: true when canvas is disabled, but mentions it in passing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded: it starts with the core purpose, then adds usage rules, then details edge cases. Every sentence adds information, but it's a bit long (around 200 words). The structure is logical, but some points could be tightened (e.g., the spill behavior). Still, it's well-organized and not redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 9 parameters and an output schema, the description covers the essential decision points: which time window to use, the exclusivity rules, data type caveats, and spill behavior. The output schema exists, so return values are documented elsewhere. The only missing piece might be a note on coordinate resolution (but that's in the schema) and potential API limits beyond what's mentioned. Given the tool's complexity, this is quite complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by summarizing common variables, explaining the mutual exclusivity of date parameters, and clarifying the 'at least one required' for hourly_variables. It also explains canvas_id's role in handling large results, which goes beyond the schema. However, some details like the exact maximum row count are left to the schema, and the description doesn't map every parameter explicitly, but it compensates well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves modeled CAMS air quality data with specific variables (PM2.5, PM10, etc.) and distinguishes it from measured station data by explicitly naming the alternative (openaq-mcp-server). It differentiates from siblings like openmeteo_get_forecast or openmeteo_get_historical by specifying the air quality domain, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance: when to use forecast_days, past_days, or start_date/end_date for archive ranges, and the exclusivity rules. It also advises against using this for measured data, pointing to openaq-mcp-server. This is clear, actionable routing guidance that prevents common misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All open-meteo-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation4/5

Each weather data tool (forecast, historical, marine, air_quality, ensemble, flood, climate) targets a distinct domain and data source, so they are largely unambiguous. However, openmeteo_get_forecast with past_days and openmeteo_get_historical overlap for recent dates, though the descriptions explicitly clarify which to use when, slightly muddying the boundary.

Naming Consistency5/5

Tool names follow a consistent openmeteo_<verb>_<object> pattern with clear actions (get, search, describe, query) and objects (forecast, historical, marine, air_quality, ensemble, flood, climate, elevation, locations, dataframe). This is highly predictable and uniform across all 11 tools.

Tool Count5/5

With 11 tools, the server covers a comprehensive set of weather data categories (forecast, historical, marine, air quality, ensemble, flood, climate, elevation) plus location search and dataframe utilities. This is well-scoped for a data-heavy weather API without being bloated, and each tool serves a distinct purpose.

Completeness5/5

The tool surface covers all major weather data needs: forecasts, historical reanalysis, marine conditions, air quality, ensemble forecasts, flood discharge, climate projections, and elevation. Location search is a proper prerequisite for coordinate-based queries, and dataframe query/describe handle large result sets, filling any gaps for data analysis workflows.

Resources